Added "ctmulq" implementation of Poly1305 (using 64->128 multiplications when available).
[BearSSL] / src / symcipher / chacha20_ct.c
1 /*
2 * Copyright (c) 2016 Thomas Pornin <pornin@bolet.org>
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining
5 * a copy of this software and associated documentation files (the
6 * "Software"), to deal in the Software without restriction, including
7 * without limitation the rights to use, copy, modify, merge, publish,
8 * distribute, sublicense, and/or sell copies of the Software, and to
9 * permit persons to whom the Software is furnished to do so, subject to
10 * the following conditions:
11 *
12 * The above copyright notice and this permission notice shall be
13 * included in all copies or substantial portions of the Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
16 * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
17 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
18 * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
19 * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
20 * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
21 * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24
25 #include "inner.h"
26
27 /* see bearssl_block.h */
28 uint32_t
29 br_chacha20_ct_run(const void *key,
30 const void *iv, uint32_t cc, void *data, size_t len)
31 {
32 unsigned char *buf;
33 uint32_t kw[8], ivw[3];
34 size_t u;
35
36 static const uint32_t CW[] = {
37 0x61707865, 0x3320646e, 0x79622d32, 0x6b206574
38 };
39
40 buf = data;
41 for (u = 0; u < 8; u ++) {
42 kw[u] = br_dec32le((const unsigned char *)key + (u << 2));
43 }
44 for (u = 0; u < 3; u ++) {
45 ivw[u] = br_dec32le((const unsigned char *)iv + (u << 2));
46 }
47 while (len > 0) {
48 uint32_t state[16];
49 int i;
50 size_t clen;
51 unsigned char tmp[64];
52
53 memcpy(&state[0], CW, sizeof CW);
54 memcpy(&state[4], kw, sizeof kw);
55 state[12] = cc;
56 memcpy(&state[13], ivw, sizeof ivw);
57 for (i = 0; i < 10; i ++) {
58
59 #define QROUND(a, b, c, d) do { \
60 state[a] += state[b]; \
61 state[d] ^= state[a]; \
62 state[d] = (state[d] << 16) | (state[d] >> 16); \
63 state[c] += state[d]; \
64 state[b] ^= state[c]; \
65 state[b] = (state[b] << 12) | (state[b] >> 20); \
66 state[a] += state[b]; \
67 state[d] ^= state[a]; \
68 state[d] = (state[d] << 8) | (state[d] >> 24); \
69 state[c] += state[d]; \
70 state[b] ^= state[c]; \
71 state[b] = (state[b] << 7) | (state[b] >> 25); \
72 } while (0)
73
74 QROUND( 0, 4, 8, 12);
75 QROUND( 1, 5, 9, 13);
76 QROUND( 2, 6, 10, 14);
77 QROUND( 3, 7, 11, 15);
78 QROUND( 0, 5, 10, 15);
79 QROUND( 1, 6, 11, 12);
80 QROUND( 2, 7, 8, 13);
81 QROUND( 3, 4, 9, 14);
82
83 #undef QROUND
84
85 }
86 for (u = 0; u < 4; u ++) {
87 br_enc32le(&tmp[u << 2], state[u] + CW[u]);
88 }
89 for (u = 4; u < 12; u ++) {
90 br_enc32le(&tmp[u << 2], state[u] + kw[u - 4]);
91 }
92 br_enc32le(&tmp[48], state[12] + cc);
93 for (u = 13; u < 16; u ++) {
94 br_enc32le(&tmp[u << 2], state[u] + ivw[u - 13]);
95 }
96
97 clen = len < 64 ? len : 64;
98 for (u = 0; u < clen; u ++) {
99 buf[u] ^= tmp[u];
100 }
101 buf += clen;
102 len -= clen;
103 cc ++;
104 }
105 return cc;
106 }